Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping

• URL: http://arxiv.org/abs/2307.08559v1
• Date: Mon, 17 Jul 2023 15:17:39 GMT
• Title: Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping
• Authors: Matthias K\"orschens, Solveig Franziska Bucher, Christine R\"omermann, Joachim Denzler
• Abstract summary: The plant community composition is an essential indicator of environmental changes and is usually analyzed in ecological field studies. We introduce an approach to interpolate the sparse labels in the collected vegetation plot time series down to the intermediate dense and unlabeled images. We also introduce a new method we call Monte-Carlo Cropping to deal with high-resolution images efficiently.
• Score: 7.993547048820065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The plant community composition is an essential indicator of environmental changes and is, for this reason, usually analyzed in ecological field studies in terms of the so-called plant cover. The manual acquisition of this kind of data is time-consuming, laborious, and prone to human error. Automated camera systems can collect high-resolution images of the surveyed vegetation plots at a high frequency. In combination with subsequent algorithmic analysis, it is possible to objectively extract information on plant community composition quickly and with little human effort. An automated camera system can easily collect the large amounts of image data necessary to train a Deep Learning system for automatic analysis. However, due to the amount of work required to annotate vegetation images with plant cover data, only few labeled samples are available. As automated camera systems can collect many pictures without labels, we introduce an approach to interpolate the sparse labels in the collected vegetation plot time series down to the intermediate dense and unlabeled images to artificially increase our training dataset to seven times its original size. Moreover, we introduce a new method we call Monte-Carlo Cropping. This approach trains on a collection of cropped parts of the training images to deal with high-resolution images efficiently, implicitly augment the training images, and speed up training. We evaluate both approaches on a plant cover dataset containing images of herbaceous plant communities and find that our methods lead to improvements in the species, community, and segmentation metrics investigated.

Related papers

• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Inside Out: Transforming Images of Lab-Grown Plants for Machine Learning Applications in Agriculture [0.0]
  We employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images. We also use our synthetic multi-plant images to train several YoloV5 nano object detection models to perform the task of plant detection.
  arXiv  Detail & Related papers  (2022-11-05T20:51:45Z)
• Semantic Image Segmentation with Deep Learning for Vine Leaf Phenotyping [59.0626764544669]
  In this study, we use Deep Learning methods to semantically segment grapevine leaves images in order to develop an automated object detection system for leaf phenotyping. Our work contributes to plant lifecycle monitoring through which dynamic traits such as growth and development can be captured and quantified.
  arXiv  Detail & Related papers  (2022-10-24T14:37:09Z)
• End-to-end deep learning for directly estimating grape yield from ground-based imagery [53.086864957064876]
  This study demonstrates the application of proximal imaging combined with deep learning for yield estimation in vineyards. Three model architectures were tested: object detection, CNN regression, and transformer models. The study showed the applicability of proximal imaging and deep learning for prediction of grapevine yield on a large scale.
  arXiv  Detail & Related papers  (2022-08-04T01:34:46Z)
• Fractional Vegetation Cover Estimation using Hough Lines and Linear Iterative Clustering [3.1654720243958128]
  This paper presents a new image processing algorithm to determine the amount of vegetation cover present in a given area. The proposed algorithm draws inspiration from the trusted Daubenmire method for vegetation cover estimation. The analysis when repeated over images captured at regular intervals of time provides crucial insights into plant growth.
  arXiv  Detail & Related papers  (2022-04-30T23:33:31Z)
• Agricultural Plant Cataloging and Establishment of a Data Framework from UAV-based Crop Images by Computer Vision [4.0382342610484425]
  We present a hands-on workflow for the automatized temporal and spatial identification and individualization of crop images from UAVs. The presented approach improves analysis and interpretation of UAV data in agriculture significantly.
  arXiv  Detail & Related papers  (2022-01-08T21:14:07Z)
• Automatic Plant Cover Estimation with CNNs Automatic Plant Cover Estimation with Convolutional Neural Networks [8.361945776819528]
  We investigate approaches using convolutional neural networks (CNNs) to automatically extract the relevant data from images. We find that we outperform our previous approach at higher image resolutions using a custom CNN with a mean absolute error of 5.16%. In addition to these investigations, we also conduct an error analysis based on the temporal aspect of the plant cover images.
  arXiv  Detail & Related papers  (2021-06-21T14:52:01Z)
• Potato Crop Stress Identification in Aerial Images using Deep Learning-based Object Detection [60.83360138070649]
  The paper presents an approach for analyzing aerial images of a potato crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of a healthy versus stressed crop at a plant level. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average Dice coefficient of 0.74.
  arXiv  Detail & Related papers  (2021-06-14T21:57:40Z)
• An embedded system for the automated generation of labeled plant images to enable machine learning applications in agriculture [1.4598479819593448]
  A lack of sufficient training data is often the bottleneck in the development of machine learning (ML) applications. We have developed an embedded robotic system to automatically generate and label large datasets of plant images. We generated a dataset of over 34,000 labeled images, with which we trained an ML-model to distinguish grasses from non-grasses.
  arXiv  Detail & Related papers  (2020-06-01T20:01:20Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)
• Automatic image-based identification and biomass estimation of invertebrates [70.08255822611812]
  Time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. We propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We use state-of-the-art Resnet-50 and InceptionV3 CNNs for the classification task.
  arXiv  Detail & Related papers  (2020-02-05T21:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.